In the real-life engineering practice, non-linear regression models have to be designed rather often. To ensure their technical or physical feasibility, such models may, in addition, require another coupling condition. This paper describes two procedures for designing a specific non-linear model using AI methods. A Radial Basis Functions (RBF) based optimization is presented of the model using Genetic Algorithms (GA). The problem solved was based on practical measurements and experiments. The results presented in the paper can be applied to many technical problems in mechanical and civil engineering and other engineering fields. and Obsahuje seznam literatury
The N250r is a face-sensitive event-related potential (ERP) deflection whose long-term memory sensitivity remains uncertain. We investigated the possibility that long-term memory-related voltage changes are represented in the early ERP's to faces but methodological considerations could affect how these changes appear to be manifested. We examined the effects of two peak analysis procedures in the assessment of the memory-sensitivity of the N250r elicited in an old/new recognition paradigm using analysis of variance (ANOVA) and artificial neural networks (ANN's). When latency was kept constant within subjects, ANOVA was unable to detect differences between ERP's to remembered and new faces; however, an ANN was. Network interpretation suggested that the ANN was detecting amplitude differences at occipitotemporal and frontocentral sites corresponding to the N250r. When peak latency was taken into account, ANOVA detected a significant decrease in onset latency of the N250r to remembered faces and amplitude differences were not detectable, even with an ANN. Results suggest that the N250r is sensitive to long-term memory. This effect may be a priming phenomenon that is attenuated at long lags between faces. Choice of peak analysis procedures is critical to the interpretation of phasic memory effects in ERP data.
The mobile robot path planning involves finding the shortest and least difficult path from a start to a goal position in a given environment without collisions with known obstacles.
The main idea of case-based reasoning (CBR) is a presumption that similar tasks probably also have similar solutions. New tasks are solved by adapting old proved solutions of similar tasks to new conditions. Tasks and their solutions (cases) are stored in a case base.
The focal point of this paper is the proposition of a path planning method based on CBR combined with graph algorithms in the environment represented by a rectangular grid. On the basis of the experimental results obtained, it is possible to say that case-based reasoning can significantly save computation costs, particularly in large environments. and Obsahuje seznam literatury
In Hungary, during the 2000s, pesticide poisoning became the most important threat for raptors, especially for the globally threatened Eastern imperial eagle (Aquila heliaca). In September 2013, with a focus on carbofuran and phorate, the first poison and carcass detection dog (PCDD) unit was formed in Hungary with a specifically trained detection dog and handler. Two more dogs were subsequently trained and joined the unit in 2017 and 2020 respectively. Between its inception until August 2020, the PCDD unit conducted 1,083 searches in five countries, which revealed 329 poisoned animals of 15 bird and nine mammal species, 120 poisoned baits and five pesticide products. Globally threatened species, including eight Eastern imperial eagles and four saker falcons (Falco cherrug), were among the detected victims. Present at 66.45% of wildlife poisoning events, the unit revealed 37.87% of the victims and 79.70% of the poisoned baits known in Hungary during the period 2013-2020. Compared to human surveys, the PCDD unit demonstrated a significantly higher find rate for poisoned baits. At 22 poisoning events (14.38% of all cases) only the PCDD unit revealed victims or poisoned baits; cases that would probably have gone undetected without the PCCD unit. Of the two focal pesticides, carbofuran was more frequently detected – in 88.56% of the positive samples. The unit played a significant role in detecting and combating wildlife poisoning incidents by deterring potential offenders and facilitating police investigations through retrieval of evidence otherwise difficult to obtain.
This article provides a critique of the use of Esping-Andersen and Kemeny’s typologies of welfare and housing regimes, both of which are often used as starting points for country selections in comparative housing research. We find that it is conceivable that housing systems may reflect the wider welfare system or diverge from it, so it is not possible to “read across” a housing system from Esping-Andersen’s welfare regimes. Moreover, both are dated and require revisiting to establish whether they still reflect reality. Of the two frameworks, Esping-Andersen’s use of the state-market-family triangle is more geographically mobile. Ultimately, housing systems are likely to be judged on the “housing outcomes” that they produce. However, it is suggested that current use of variables within EU-SILC in order to establish “housing outcomes” may be misleading since they do not reflect acceptable standards between countries with greatly differing general living standards and cultural norms.
Relations between two Boolean attributes derived from data can be
quantified by truth functions defined on four-fold tables corresponding to pairs of the attributes. Several classes of such quantifiers (implicational, double implicational, equivalence ones) with truth values in the unit interval were investigated in the frame of the theory of data mining methods. In the fuzzy logic theory, there are well-defined classes of fuzzy operators, namely t-norms representing various types of evaluations of fuzzy conjunction (and t-conorms representing fuzzy disjunction), and operators of fuzzy implications.
In the contribution, several types of constructions of quantifiers using fuzzy operators are described. Definitions and theorems presented by the author in previous contributions to WUPES workshops are summarized and illustrated by examples of well-known quantifiers and operators.
There is growing interest to analyze electroencephalogram (EEG) signals with the objective of classifying schizophrenic patients from the control subjects. In this study, EEG signals of 15 schizophrenic patients and 19 age-matched control subjects are recorded using twenty surface electrodes. After the preprocessing phase, several features including autoregressive (AR) model coefficients, band power and fractal dimension were extracted from their recorded signals. Three classifiers including Linear Discriminant Analysis (LDA), Multi-LDA (MLDA) and Adaptive Boosting (Adaboost) were implemented to classify the EEG features of schizophrenic and normal subjects. Leave-one (participant)-out cross validation is performed in the training phase and finally in the test phase; the results of applying the LDA, MLDA and Adaboost respectively provided 78%, 81% and 82% classification accuracies between the two groups. For further improvement, Genetic Programming (GP) is employed to select more informative features and remove the redundant ones. After applying GP on the feature vectors, the results are remarkably improved so that the classification rate of the two groups with LDA, MLDA and Adaboost classifiers yielded 82%, 84% and 93% accuracies, respectively.